© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Qwen3-4B
    5. 22-TRANSCODER-HP
    7. 86752
    Prev
    Next
    INDEX
    Explanations

    metadata tags

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    mwhanna/qwen3-4b-transcoders/layer_22.safetensors
    Prompts (Dashboard)
    16,384 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    Features
    163,840
    Data Type
    float32
    Hook Name
    blocks.22.mlp.hook_in
    Architecture
    transcoder
    Context Size
    8,192
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Negative Logits
    åŃIJéĩĮ
    -0.28
    acier
    -0.26
    æŃ£
    -0.25
    çĬ¶
    -0.25
    çon
    -0.25
    ordinate
    -0.24
    ⨯
    -0.24
    üns
    -0.23
    .ndarray
    -0.23
    åĿıäºĭ
    -0.23
    POSITIVE LOGITS
    lez
    0.27
     cooperative
    0.26
     fiscal
    0.25
    getExtension
    0.25
    atical
    0.24
    gil
    0.24
    anal
    0.24
    çIJĨäºĭä¼ļ
    0.24
    inding
    0.24
    æĶ¯
    0.24
    Activations Density 0.010%

    No Known Activations